GPT-5.4 vs GPT-6.1 Sol
Wins 0 of 8 areas
—
Wins 7 of 8 areas
Coding · Agents · Reasoning · Facts · Math · Long documents · Following instructions
GPT-6.1 Sol is the stronger all-rounder.
Scores updated · 32 tests both models report · How we compare
Where each one wins
Tests won in each of the eight areas we test. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- ReasoningHard problems that need careful thinking05GPT-6.1 Sol5 of 5 tests
- FactsGetting facts right instead of making them up03GPT-6.1 Sol3 of 3 tests
- MathCompetition and research-level math03GPT-6.1 Sol3 of 3 tests
- AgentsCarrying out multi-step tasks on its own02GPT-6.1 Sol2 of 2 tests
- CodingWriting and fixing software12GPT-6.1 Sol2 of 4 tests · 1 tie
- Long documentsFinding answers in very long texts01GPT-6.1 Sol1 of 1 test
- Following instructionsDoing exactly what it is asked01GPT-6.1 Sol1 of 1 test
- Images and chartsUnderstanding pictures, charts and video11Even1 each
Long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
GPT-6.1 Sol costs 31% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GPT-6.1 Sol pulls ahead
- Solves new puzzle games it has never seenARC-AGI-3+52.5points ahead
- Extremely hard research-level math problemsFrontierMath Tier 4+51points ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+37.4points ahead
Where GPT-5.4 pulls ahead
- Code for real scientific research problemsSciCode+2.4points ahead
Every test, side by side
All 32 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingGPT-6.1 Sol
- LMArena · WebDevGPT-6.1 Sol by 281 rating points14621743+281 rating
- LiveBench · CodingGPT-6.1 Sol by 2.977.580.4+2.9
- SciCodeGPT-5.4 by 2.456.654.2+2.4
- LiveBench · Agentic Codingtie53.854.5tie
AgentsGPT-6.1 Sol
- AA ApexAgentsGPT-6.1 Sol by 26.733.360+26.7
- GDPValGPT-6.1 Sol by 17.437.354.7+17.4
ReasoningGPT-6.1 Sol
- ARC-AGI-3GPT-6.1 Sol by 52.50.252.7+52.5
- ARC-AGI-2GPT-6.1 Sol by 20.973.394.2+20.9
- Humanity's Last ExamGPT-6.1 Sol by 9.243.752.9+9.2
- CritPtGPT-6.1 Sol by 8.323.431.7+8.3
- LiveBench · ReasoningGPT-6.1 Sol by 4.588.192.6+4.5
FactsGPT-6.1 Sol
- AA-Omniscience · Non-hallucinationGPT-6.1 Sol by 37.48.345.7+37.4
- SimpleQA VerifiedGPT-6.1 Sol by 28.845.173.9+28.8
- AA-Omniscience · AccuracyGPT-6.1 Sol by 11.250.962.1+11.2
Images and chartsEven
- MMMU-ProGPT-6.1 Sol by 7.678.486+7.6
- LMArena · VisionGPT-5.4 by 15 rating points13011286+15 rating
MathGPT-6.1 Sol
- FrontierMath Tier 4GPT-6.1 Sol by 5149100+51
- FrontierMath Tiers 1-3 (v2)GPT-6.1 Sol by 15.178.693.7+15.1
- LiveBench · MathematicsGPT-6.1 Sol by 2.694.296.8+2.6
Following instructionsGPT-6.1 Sol
- LiveBench · Instruction FollowingGPT-6.1 Sol by 470.274.2+4
Other results11 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- HiL-Bench (Tools-allowed)GPT-6.1 Sol by 52.69.762.3+52.6
- AA-OmniscienceGPT-6.1 Sol by 35.75.841.5+35.7
- DeepSWE 1.1GPT-6.1 Sol by 23.25275.2+23.2
- HealthBench Professional length-adjustedGPT-6.1 Sol by 16.148.164.2+16.1
- AA IntelligenceGPT-6.1 Sol by 12.83951.8+12.8
- livebench_languageGPT-6.1 Sol by 7.582.690.1+7.5
- HealthBench Hard length-adjustedGPT-6.1 Sol by 7.129.136.2+7.1
- HealthBench length-adjustedGPT-6.1 Sol by 4.55458.5+4.5
- livebench_data_analysisGPT-6.1 Sol by 3.479.382.7+3.4
- ARC-AGI-1GPT-6.1 Sol by 2.893.796.5+2.8
- HealthBench Consensus length-adjustedtie96.396tie
Questions people ask
Which is better, GPT-5.4 or GPT-6.1 Sol?
GPT-6.1 Sol wins seven of the eight areas we test: coding, agents, reasoning, facts, math, long documents and following instructions. GPT-5.4 wins none. They are level on images and charts.
Which is better for coding?
GPT-6.1 Sol. It wins 2 of the 4 coding tests both models report; GPT-5.4 wins 1, and 1 is a tie.
Which is cheaper?
GPT-5.4 costs $2.50 per million input tokens and $15.00 per million output tokens; GPT-6.1 Sol costs $2.00 and $10.00. That makes GPT-6.1 Sol about 31% cheaper for the same work.
How do you compare the two?
We use the 32 benchmark tests both models have published scores on. The verdict counts the 21 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 11 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.